DocumentCode
1930978
Title
Notice of Retraction
The application of optimal weights initialization algorithm based on information amount in multi-layer perceptron networks
Author
Xiao Wei ; Yan Xiu-tao
Author_Institution
Dept. of Electron., Tibet Univ., Lhasa, China
Volume
6
fYear
2010
fDate
9-11 July 2010
Firstpage
196
Lastpage
198
Abstract
Notice of Retraction
After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.
We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.
The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.
In this paper, considering fluctuations of weights (infromation amount) and influence of different sample sets, an optimization criteria function is constructed to determine the matching degree between current sample sets and initial weight sets, therefore, an optimal weight sets are achieved as intial weight sets to the neural network. Actual test shows that the algorithm makes the convergence speed of neural network evidently improved, and is suitable for embedded system.
After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.
We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.
The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.
In this paper, considering fluctuations of weights (infromation amount) and influence of different sample sets, an optimization criteria function is constructed to determine the matching degree between current sample sets and initial weight sets, therefore, an optimal weight sets are achieved as intial weight sets to the neural network. Actual test shows that the algorithm makes the convergence speed of neural network evidently improved, and is suitable for embedded system.
Keywords
multilayer perceptrons; embedded system; information amount; multi-layer perceptron networks; neural network; optimal weights initialization algorithm; optimization criteria function; Educational institutions; Genetics; an optimization criteria function; embedded system; fluctuations of weights; matching degree; sample sets;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer Science and Information Technology (ICCSIT), 2010 3rd IEEE International Conference on
Conference_Location
Chengdu
Print_ISBN
978-1-4244-5537-9
Type
conf
DOI
10.1109/ICCSIT.2010.5563702
Filename
5563702
Link To Document